{"id":"https://openalex.org/W7138095983","doi":"https://doi.org/10.1609/aaai.v40i31.39859","title":"LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding","display_name":"LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138095983","doi":"https://doi.org/10.1609/aaai.v40i31.39859"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i31.39859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39859","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129726866","display_name":"Xiaodong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123594243","display_name":"Langling Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Langling Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123628414","display_name":"Zhirong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhirong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694720","display_name":"Xu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721699","display_name":"Teng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123541415","display_name":"Xuhong Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuhong Xia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641052","display_name":"Peixi Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129726866"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40343028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26517","last_page":"26525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9714000225067139,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9714000225067139,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8330000042915344},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8057000041007996},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6990000009536743},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5745999813079834},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/interactive-video","display_name":"Interactive video","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460999727249146},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8330000042915344},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8057000041007996},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C86297840","wikidata":"https://www.wikidata.org/wiki/Q6045397","display_name":"Interactive design","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C203004452","wikidata":"https://www.wikidata.org/wiki/Q1186952","display_name":"Interactive media","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26649999618530273}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i31.39859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4136253297328949,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,78],"development":[1],"of":[2,49,118,154],"multimodal":[3],"large":[4],"language":[5],"models":[6,165,177],"(MLLMs)":[7],"has":[8],"advanced":[9],"general":[10,185],"video":[11,15,90,186],"understanding.":[12],"However,":[13],"existing":[14],"evaluation":[16],"benchmarks":[17],"primarily":[18],"focus":[19],"on":[20,143,178,184],"non-interactive":[21],"videos,":[22,42,120],"such":[23],"as":[24],"movies":[25],"and":[26,56,92,110,126,180,192],"recordings.":[27],"To":[28,59,114],"fill":[29],"this":[30,32],"gap,":[31],"paper":[33],"proposes":[34],"the":[35,53,62,73,105,135,172],"first":[36],"omnimodal":[37],"benchmark":[38,106],"for":[39,88],"interactive":[40,102,119,155],"livestream":[41],"LiViBench.":[43],"It":[44],"features":[45],"a":[46,66,85,94,128],"diverse":[47],"set":[48],"24":[50],"tasks,":[51],"highlighting":[52],"perceptual,":[54],"reasoning,":[55],"livestream-specific":[57],"challenges.":[58],"efficiently":[60],"construct":[61,98],"dataset,":[63],"we":[64,121,146],"design":[65,122],"standardized":[67],"semi-automatic":[68],"annotation":[69],"workflow":[70,79],"that":[71,159],"incorporates":[72],"human-in-the-loop":[74],"at":[75],"multiple":[76,81],"stages.":[77],"leverages":[80],"MLLMs":[82],"to":[83,97,133,138,168],"form":[84],"multi-agent":[86],"system":[87],"comprehensive":[89],"description":[91],"uses":[93],"seed-question-driven":[95],"method":[96],"high-quality":[99],"annotations.":[100],"All":[101],"videos":[103],"in":[104],"include":[107],"audio,":[108],"speech,":[109],"real-time":[111,140],"comments":[112],"modalities.":[113],"enhance":[115],"models'":[116],"understanding":[117],"tailored":[123],"two-stage":[124],"instruction-tuning":[125],"propose":[127],"Video-to-Comment":[129],"Retrieval":[130],"(VCR)":[131],"module":[132],"improve":[134],"model's":[136],"ability":[137],"utilize":[139],"comments.":[141],"Based":[142],"these":[144],"advancements,":[145],"develop":[147],"LiVi-LLM-7B,":[148],"an":[149],"MLLM":[150],"with":[151,166,174],"enhanced":[152,182],"knowledge":[153],"livestreams.":[156],"Experiments":[157],"show":[158],"our":[160],"model":[161],"outperforms":[162],"larger":[163],"open-source":[164],"up":[167],"72B":[169],"parameters,":[170],"narrows":[171],"gap":[173],"leading":[175],"proprietary":[176],"LiViBench,":[179],"achieves":[181],"performance":[183],"benchmarks,":[187],"including":[188],"VideoMME,":[189],"LongVideoBench,":[190],"MLVU,":[191],"VideoEval-Pro.":[193]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}